Merge branch 'akpm'(patches from Andrew)

Merge fixes from Andrew Morton:
 "10 fixes"

The lockdep hlist conversion is in the locking tree too, waiting for the
next merge window.  Andrew thought it should go in now.  I'll take it,
since it fixes a real problem and looks trivially correct (famous last
words).

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  arch/x86/Kconfig: CONFIG_X86_UV should depend on CONFIG_EFI
  mm: fix pfn_t vs highmem
  kernel/locking/lockdep.c: convert hash tables to hlists
  mm,thp: fix spellos in describing __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
  mm,thp: khugepaged: call pte flush at the time of collapse
  mm/backing-dev.c: fix error path in wb_init()
  mm, dax: check for pmd_none() after split_huge_pmd()
  vsprintf: kptr_restrict is okay in IRQ when 2
  mm: fix filemap.c kernel doc warning
  ubsan: cosmetic fix to Kconfig text

arch/x86/Kconfig

@@ -475,6 +475,7 @@ config X86_UV
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
+	depends on EFI
 	depends on X86_X2APIC
 	depends on PCI
 	---help---

include/linux/lockdep.h

@@ -66,7 +66,7 @@ struct lock_class {
 	/*
 	 * class-hash:
 	 */
-	struct list_head		hash_entry;
+	struct hlist_node		hash_entry;
 
 	/*
 	 * global list of all lock-classes:
@@ -199,7 +199,7 @@ struct lock_chain {
 	u8				irq_context;
 	u8				depth;
 	u16				base;
-	struct list_head		entry;
+	struct hlist_node		entry;
 	u64				chain_key;
 };
 

include/linux/pfn.h

@@ -10,7 +10,7 @@
  * backing is indicated by flags in the high bits of the value.
  */
 typedef struct {
-	unsigned long val;
+	u64 val;
 } pfn_t;
 #endif
 

include/linux/pfn_t.h

@@ -9,14 +9,13 @@
  * PFN_DEV - pfn is not covered by system memmap by default
  * PFN_MAP - pfn has a dynamic page mapping established by a device driver
  */
-#define PFN_FLAGS_MASK (((unsigned long) ~PAGE_MASK) \
-		<< (BITS_PER_LONG - PAGE_SHIFT))
-#define PFN_SG_CHAIN (1UL << (BITS_PER_LONG - 1))
-#define PFN_SG_LAST (1UL << (BITS_PER_LONG - 2))
-#define PFN_DEV (1UL << (BITS_PER_LONG - 3))
-#define PFN_MAP (1UL << (BITS_PER_LONG - 4))
-
-static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, unsigned long flags)
+#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
+#define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
+#define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
+#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
+#define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
+
+static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
 {
 	pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), };
 
@@ -29,7 +28,7 @@ static inline pfn_t pfn_to_pfn_t(unsigned long pfn)
 	return __pfn_to_pfn_t(pfn, 0);
 }
 
-extern pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags);
+extern pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags);
 
 static inline bool pfn_t_has_page(pfn_t pfn)
 {
@@ -87,7 +86,7 @@ static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot)
 #ifdef __HAVE_ARCH_PTE_DEVMAP
 static inline bool pfn_t_devmap(pfn_t pfn)
 {
-	const unsigned long flags = PFN_DEV|PFN_MAP;
+	const u64 flags = PFN_DEV|PFN_MAP;
 
 	return (pfn.val & flags) == flags;
 }

kernel/locking/lockdep.c

@@ -292,7 +292,7 @@ LIST_HEAD(all_lock_classes);
 #define __classhashfn(key)	hash_long((unsigned long)key, CLASSHASH_BITS)
 #define classhashentry(key)	(classhash_table + __classhashfn((key)))
 
-static struct list_head classhash_table[CLASSHASH_SIZE];
+static struct hlist_head classhash_table[CLASSHASH_SIZE];
 
 /*
  * We put the lock dependency chains into a hash-table as well, to cache
@@ -303,7 +303,7 @@ static struct list_head classhash_table[CLASSHASH_SIZE];
 #define __chainhashfn(chain)	hash_long(chain, CHAINHASH_BITS)
 #define chainhashentry(chain)	(chainhash_table + __chainhashfn((chain)))
 
-static struct list_head chainhash_table[CHAINHASH_SIZE];
+static struct hlist_head chainhash_table[CHAINHASH_SIZE];
 
 /*
  * The hash key of the lock dependency chains is a hash itself too:
@@ -666,7 +666,7 @@ static inline struct lock_class *
 look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 {
 	struct lockdep_subclass_key *key;
-	struct list_head *hash_head;
+	struct hlist_head *hash_head;
 	struct lock_class *class;
 
 #ifdef CONFIG_DEBUG_LOCKDEP
@@ -719,7 +719,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return NULL;
 
-	list_for_each_entry_rcu(class, hash_head, hash_entry) {
+	hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key) {
 			/*
 			 * Huh! same key, different name? Did someone trample
@@ -742,7 +742,7 @@ static inline struct lock_class *
 register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 {
 	struct lockdep_subclass_key *key;
-	struct list_head *hash_head;
+	struct hlist_head *hash_head;
 	struct lock_class *class;
 
 	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
@@ -774,7 +774,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * We have to do the hash-walk again, to avoid races
 	 * with another CPU:
 	 */
-	list_for_each_entry_rcu(class, hash_head, hash_entry) {
+	hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key)
 			goto out_unlock_set;
 	}
@@ -805,7 +805,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * We use RCU's safe list-add method to make
 	 * parallel walking of the hash-list safe:
 	 */
-	list_add_tail_rcu(&class->hash_entry, hash_head);
+	hlist_add_head_rcu(&class->hash_entry, hash_head);
 	/*
 	 * Add it to the global list of classes:
 	 */
@@ -2017,7 +2017,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 				     u64 chain_key)
 {
 	struct lock_class *class = hlock_class(hlock);
-	struct list_head *hash_head = chainhashentry(chain_key);
+	struct hlist_head *hash_head = chainhashentry(chain_key);
 	struct lock_chain *chain;
 	struct held_lock *hlock_curr;
 	int i, j;
@@ -2033,7 +2033,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	 * We can walk it lock-free, because entries only get added
 	 * to the hash:
 	 */
-	list_for_each_entry_rcu(chain, hash_head, entry) {
+	hlist_for_each_entry_rcu(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
 			debug_atomic_inc(chain_lookup_hits);
@@ -2057,7 +2057,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	/*
 	 * We have to walk the chain again locked - to avoid duplicates:
 	 */
-	list_for_each_entry(chain, hash_head, entry) {
+	hlist_for_each_entry(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 			graph_unlock();
 			goto cache_hit;
@@ -2091,7 +2091,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 		}
 		chain_hlocks[chain->base + j] = class - lock_classes;
 	}
-	list_add_tail_rcu(&chain->entry, hash_head);
+	hlist_add_head_rcu(&chain->entry, hash_head);
 	debug_atomic_inc(chain_lookup_misses);
 	inc_chains();
 
@@ -3875,7 +3875,7 @@ void lockdep_reset(void)
 	nr_process_chains = 0;
 	debug_locks = 1;
 	for (i = 0; i < CHAINHASH_SIZE; i++)
-		INIT_LIST_HEAD(chainhash_table + i);
+		INIT_HLIST_HEAD(chainhash_table + i);
 	raw_local_irq_restore(flags);
 }
 
@@ -3894,7 +3894,7 @@ static void zap_class(struct lock_class *class)
 	/*
 	 * Unhash the class and remove it from the all_lock_classes list:
 	 */
-	list_del_rcu(&class->hash_entry);
+	hlist_del_rcu(&class->hash_entry);
 	list_del_rcu(&class->lock_entry);
 
 	RCU_INIT_POINTER(class->key, NULL);
@@ -3917,7 +3917,7 @@ static inline int within(const void *addr, void *start, unsigned long size)
 void lockdep_free_key_range(void *start, unsigned long size)
 {
 	struct lock_class *class;
-	struct list_head *head;
+	struct hlist_head *head;
 	unsigned long flags;
 	int i;
 	int locked;
@@ -3930,9 +3930,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
 	 */
 	for (i = 0; i < CLASSHASH_SIZE; i++) {
 		head = classhash_table + i;
-		if (list_empty(head))
-			continue;
-		list_for_each_entry_rcu(class, head, hash_entry) {
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
 			if (within(class->key, start, size))
 				zap_class(class);
 			else if (within(class->name, start, size))
@@ -3962,7 +3960,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
 void lockdep_reset_lock(struct lockdep_map *lock)
 {
 	struct lock_class *class;
-	struct list_head *head;
+	struct hlist_head *head;
 	unsigned long flags;
 	int i, j;
 	int locked;
@@ -3987,9 +3985,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 	locked = graph_lock();
 	for (i = 0; i < CLASSHASH_SIZE; i++) {
 		head = classhash_table + i;
-		if (list_empty(head))
-			continue;
-		list_for_each_entry_rcu(class, head, hash_entry) {
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
 			int match = 0;
 
 			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
@@ -4027,10 +4023,10 @@ void lockdep_init(void)
 		return;
 
 	for (i = 0; i < CLASSHASH_SIZE; i++)
-		INIT_LIST_HEAD(classhash_table + i);
+		INIT_HLIST_HEAD(classhash_table + i);
 
 	for (i = 0; i < CHAINHASH_SIZE; i++)
-		INIT_LIST_HEAD(chainhash_table + i);
+		INIT_HLIST_HEAD(chainhash_table + i);
 
 	lockdep_initialized = 1;
 }

kernel/memremap.c

@@ -150,7 +150,7 @@ void devm_memunmap(struct device *dev, void *addr)
 }
 EXPORT_SYMBOL(devm_memunmap);
 
-pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
+pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags)
 {
 	return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
 }

lib/Kconfig.ubsan

@@ -18,6 +18,8 @@ config UBSAN_SANITIZE_ALL
 	  This option activates instrumentation for the entire kernel.
 	  If you don't enable this option, you have to explicitly specify
 	  UBSAN_SANITIZE := y for the files/directories you want to check for UB.
+	  Enabling this option will get kernel image size increased
+	  significantly.
 
 config UBSAN_ALIGNMENT
 	bool "Enable checking of pointers alignment"
@@ -25,5 +27,5 @@ config UBSAN_ALIGNMENT
 	default y if !HAVE_EFFICIENT_UNALIGNED_ACCESS
 	help
 	  This option enables detection of unaligned memory accesses.
-	  Enabling this option on architectures that support unalligned
+	  Enabling this option on architectures that support unaligned
 	  accesses may produce a lot of false positives.

lib/vsprintf.c

@@ -1590,22 +1590,23 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 			return buf;
 		}
 	case 'K':
-		/*
-		 * %pK cannot be used in IRQ context because its test
-		 * for CAP_SYSLOG would be meaningless.
-		 */
-		if (kptr_restrict && (in_irq() || in_serving_softirq() ||
-				      in_nmi())) {
-			if (spec.field_width == -1)
-				spec.field_width = default_width;
-			return string(buf, end, "pK-error", spec);
-		}
-
 		switch (kptr_restrict) {
 		case 0:
 			/* Always print %pK values */
 			break;
 		case 1: {
+			const struct cred *cred;
+
+			/*
+			 * kptr_restrict==1 cannot be used in IRQ context
+			 * because its test for CAP_SYSLOG would be meaningless.
+			 */
+			if (in_irq() || in_serving_softirq() || in_nmi()) {
+				if (spec.field_width == -1)
+					spec.field_width = default_width;
+				return string(buf, end, "pK-error", spec);
+			}
+
 			/*
 			 * Only print the real pointer value if the current
 			 * process has CAP_SYSLOG and is running with the
@@ -1615,8 +1616,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 			 * leak pointer values if a binary opens a file using
 			 * %pK and then elevates privileges before reading it.
 			 */
-			const struct cred *cred = current_cred();
-
+			cred = current_cred();
 			if (!has_capability_noaudit(current, CAP_SYSLOG) ||
 			    !uid_eq(cred->euid, cred->uid) ||
 			    !gid_eq(cred->egid, cred->gid))

mm/backing-dev.c

@@ -328,7 +328,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	return 0;
 
 out_destroy_stat:
-	while (--i)
+	while (i--)
 		percpu_counter_destroy(&wb->stat[i]);
 	fprop_local_destroy_percpu(&wb->completions);
 out_put_cong:

mm/filemap.c

@@ -1890,6 +1890,7 @@ EXPORT_SYMBOL(generic_file_read_iter);
  * page_cache_read - adds requested page to the page cache if not already there
  * @file:	file to read
  * @offset:	page index
+ * @gfp_mask:	memory allocation flags
  *
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.

mm/mprotect.c

@@ -160,9 +160,11 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		}
 
 		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
-			if (next - addr != HPAGE_PMD_SIZE)
+			if (next - addr != HPAGE_PMD_SIZE) {
 				split_huge_pmd(vma, pmd, addr);
-			else {
+				if (pmd_none(*pmd))
+					continue;
+			} else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
 						newprot, prot_numa);
 

mm/mremap.c

@@ -210,6 +210,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				}
 			}
 			split_huge_pmd(vma, old_pmd, old_addr);
+			if (pmd_none(*old_pmd))
+				continue;
 			VM_BUG_ON(pmd_trans_huge(*old_pmd));
 		}
 		if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma,

mm/pgtable-generic.c

@@ -90,9 +90,9 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
  * ARCHes with special requirements for evicting THP backing TLB entries can
  * implement this. Otherwise also, it can help optimize normal TLB flush in
  * THP regime. stock flush_tlb_range() typically has optimization to nuke the
- * entire TLB TLB if flush span is greater than a threshhold, which will
+ * entire TLB if flush span is greater than a threshold, which will
  * likely be true for a single huge page. Thus a single thp flush will
- * invalidate the entire TLB which is not desitable.
+ * invalidate the entire TLB which is not desirable.
  * e.g. see arch/arc: flush_pmd_tlb_range
  */
 #define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
@@ -195,7 +195,9 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(pmd_trans_huge(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
-	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	/* collapse entails shooting down ptes not pmd */
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
 }
 #endif